Improving Sentence Similarity Estimation for Unsupervised Extractive Summarization
This work addresses a bottleneck in unsupervised extractive summarization for NLP applications, but it is incremental as it builds on existing similarity-based methods.
The paper tackled the problem of weak correlation between sentence similarity estimation and salience ranking in unsupervised extractive summarization by proposing two strategies: contrastive learning for document-level optimization and mutual learning with a signal amplifier, resulting in improved performance as demonstrated in experiments.
Unsupervised extractive summarization aims to extract salient sentences from a document as the summary without labeled data. Recent literatures mostly research how to leverage sentence similarity to rank sentences in the order of salience. However, sentence similarity estimation using pre-trained language models mostly takes little account of document-level information and has a weak correlation with sentence salience ranking. In this paper, we proposed two novel strategies to improve sentence similarity estimation for unsupervised extractive summarization. We use contrastive learning to optimize a document-level objective that sentences from the same document are more similar than those from different documents. Moreover, we use mutual learning to enhance the relationship between sentence similarity estimation and sentence salience ranking, where an extra signal amplifier is used to refine the pivotal information. Experimental results demonstrate the effectiveness of our strategies.